检索结果-内蒙古大学图书馆

17th International Conference on Frontiers of Information technology, FIT 2019

作者： Aslam, Sheraz Herodotou, Herodotos Ayub, Nasir Mohsin, Syed Muhammad Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology Limassol3025 Cyprus Department of Computer Science COMSATS University Islamabad Islamabad45550 Pakistan Federal Urdu University of Arts Science and Technology Islamabad44000 Pakistan

ISBN: (纸本)9781728166254

In the last few years, carbon emissions and energy demand have increased dramatically around the globe due to a surge in population and energy-consuming devices. The integration of renewable energy resources (RERs) in a power supply system provides an efficient solution in terms of low energy cost with lower carbon emissions. However, renewable sources like solar panels have irregular nature of power generation because of their dependence on weather conditions, such as solar radiation, humidity, and temperature. Therefore, to tackle this intermittent nature of solar energy, power prediction is necessary for efficient energy management. Deep learning and machine learning-based methods have frequently been implemented for energy forecasting in the literature. The current work summarizes the state-of-theart deep learning-based methods that are proposed to forecast the solar power for proper energy management. We also explain the methodologies of solar energy forecasting along with their outcomes. At the end, future challenges and opportunities are uncovered in the application of deep and machine learning in this area. © 2019 IEEE.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization for Standalone Virtual Reality Headsets

Performance Optimization for Standalone Virtual Reality Head...

引用

IEEE Conference on Graphics and media (GAME)

作者： Youssef Samir Sadek Hosny Mohammed A.-M Salem Ahmed Wahby Computer Science and Engineering Faculty of Media Eng. and Technology German University in Cairo Egypt Faculty of Media Eng. and Technology German University in Cairo Egypt Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt Faculty of Applied Sciences and Arts German University in Cairo Egypt

ISBN: (数字)9781728192444

ISBN: (纸本)9781728192451

This paper focuses on the performance optimization process for standalone virtual reality headsets. With the release of the Oculus Quest on May 2019, and its wide adoption, developing a VR application is not as simple as it used to be on regular PCVR headsets, which run on VR ready desktops powered by dedicated processors and graphics cards. The mobile processor of standalone headsets is much weaker than the ones on a dedicated VR computer. Therefore, heavy performance optimization is needed in order to run full scale applications on the Oculus Quest without facing application slow downs and performance drops. PlayBricks; A VR application running on the Oculus Quest using Unreal Engine 4 and C++, is developed to simulate real life LEGOs for architectural design and educational applications. The hardest problem faced in development is the performance problem, where the number of blocks the user places before the application starts slowing down is not enough to build anything meaningful. Through the optimization of the CPU, GPU and draw call threads, the paper reveals how the number of building blocks can be increased from 100 blocks to reach 12,000 blocks.

关键词： Games Optimization Engines Headphones Tools Graphics processing units Education

来源：评论

学校读者我要写书评

暂无评论

IoT Architecture for Enhancing Rural Societal Services in Sub-Saharan Africa

引用

Procedia computer Science 2020年 177卷 338-344页

作者： Ethiopia Nigussie Thomas O. Olwal Atli Lemma Fisseha Mekuria Bo Peterson Department of Future Technologies University of Turku Turku Finland Department of Electrical Engineering/F’SATI Tshwane University of Technology Pretoria South Africa School of Electrical Engineering Haramaya University Dire Dawa Ethiopia Council for Scientific and Industrial Research Pretoria South Africa Department for Computer Science and Media Technology Malmö University Malmö Sweden

The potential of IoT in contributing towards sustainable economic development in Sub-Saharan Africa (SSA) through digital transformation and effective service delivery is widely accepted. However, the unreliability/unavailability of connectivity and power grid infrastructure as well as the unaffordability of the overall system hinders the implementation of a multi-layered IoT architecture for rural societal services in SSA. In this work, affordable IoT architecture that operates without reliance on broadband connectivity and power grid is developed. The architecture employs energy harvesting system and performs data processing, actuation decisions and network management locally by integrating a customized low-cost computationally capable device with the gateway. The sharing of this device among the water resource and quality management, healthcare and agriculture applications further reduces the overall system cost. The evaluation of LPWAN technologies reveals that LoRaWAN has lower cost with added benefits of adaptive data rate and largest community support while providing comparable performance and communication range with the other technologies. The relevant results of the analysis is communicated to end-users’ mobile device via 2G/3G GPRS. Hence, the proposed IoT architecture enables the implementation of IoT systems for improving efficiency in three key application areas at low cost.

关键词： IoT architecture Connectivity technologies Sub-Saharan Africa Healthcare Agriculture Water quality resources management

来源：评论

学校读者我要写书评

暂无评论

Dynamic Risk Assessment and Certification in the Power Grid: A Collaborative Approach

Dynamic Risk Assessment and Certification in the Power Grid:...

引用

IEEE Conference on Network Softwarization (NetSoft)

作者： Athanasios Liatifis Pedro Ruzafa Alcazar Panagiotis Radoglou Grammatikis Dimitris Papamartzivanos Sofianna Menesidou Thomas Krousarlis Molinuevo Martin Alberto Iñ aki Angulo Antonios Sarigiannidis Thomas Lagkas Vasileios Argyriou Antonio Skarmeta Panagiotis Sarigiannidis Department of Electrical and Computer Engineering University of Western Macedonia Kozani Greece Department of Information and Communications Engineering University of Murcia Murcia Spain UBITECH Limited 26 Nikou &#x0026 Despinas Pattchi Limassol Cyprus TECNALIA Basque Research and Technology Alliance (BRTA) Parque Cientifico Y Tecnologico De Bizkaia Astondo Bidea Edificio 700 Derio Bizkaia Spain Sidroco Holdings Ltd Nicosia Cyprus Department of Computer Science Kavala Campus International Hellenic University Greece Department of Networks and Digital Media Penrhyn Road Kingston upon Thames Kingston University London Surrey UK

ISBN: (数字)9781665406949

ISBN: (纸本)9781665406956

The digitisation of the typical electrical grid introduces valuable services, such as pervasive control, remote monitoring and self-healing. However, despite the benefits, cybersecurity and privacy issues can result in devastating effects or even fatal accidents, given the interdependence between the energy sector and other critical infrastructures. Large-scale cyber attacks, such as Indostroyer and DragonFly have already demonstrated the weaknesses of the current electrical grid with disastrous consequences. Based on the aforementioned remarks, both academia and industry have already designed various cybersecurity standards, such as IEC 62351. However, dynamic risk assessment and certification remain crucial aspects, given the sensitive nature of the electrical grid. On the one hand, dynamic risk assessment intends to re-compute the risk value of the affected assets and their relationships in a dynamic manner based on the relevant security events and alarms. On the other hand, based on the certification process, new approach for the dynamic management of the security need to be defined in order to provide adaptive reaction to new threats. This paper presents a combined approach, showing how both aspects can be applied in a collaborative manner in the smart electrical grid.

关键词： Privacy Power system dynamics Collaboration Random access memory Production Smart grids Risk management

来源：评论

学校读者我要写书评

暂无评论

Partial differential equations of entropy analysis on ternary hybridity nanofluid flow model via rotating disk with hall current and electromagnetic radiative influences

引用

Scientific Reports 2022年第1期12卷 1-24页

作者： Al Oweidi, Khalid Fanoukh Shahzad, Faisal Jamshed, Wasim Usman Ibrahim, Rabha W. El Din, El Sayed M. Tag AlDerea, Afrah M. Department of Water Resources Management Engineering College of Engineering Al-Qasim Green University Babylon Iraq Department of Mathematics Capital University of Science and Technology (CUST) Islamabad 44000 Pakistan Department of Computer Science National University of Sciences and Technology Balochistan Campus (NBC) Quetta 87300 Pakistan Department of Mathematics Mathematics Research Center Near East University Near East Boulevard Nicosia/Mersin 10 99138 Turkey Departement of Electrical Engineering Faculty of Engineering and Technology Future University New Cairo 11835 Egypt Department of Mathematics College of Science and Arts Qassim University 51951 Al-Badaya Saudi Arabia

The flow of a fluid across a revolving disc has several technical and industrial uses. Examples of rotating disc flows include centrifugal pumps, viscometers, rotors, fans, turbines, and spinning discs. An important technology with implications for numerous treatments utilized in numerous sectors is the use of hybrid nanofluids (HNFs) to accelerate current advancements. Through investigation of ternary nanoparticle impacts on heat transfer (HT) and liquid movement, the thermal properties of tri-HNFs were to be ascertained in this study. Hall current, thermal radiation, and heat dissipation have all been studied in relation to the use of flow-describing equations. The ternary HNFs under research are composed of the nanomolecules aluminum oxide (Al₂O₃), copper oxide (CuO), silver (Ag), and water (H₂O). For a number of significant physical characteristics, the physical situation is represented utilizing the boundary layer investigation, which produces partial differential equations (PDEs). The rheology of the movement is extended and computed in a revolving setting under the assumption that the movement is caused by a rotatingfloppy. Before the solution was found using the finite difference method, complicated generated PDEs were transformed into corresponding ODEs (Keller Box method). A rise in the implicated influencing factors has numerous notable physical impacts that have been seen and recorded. The Keller Box method (KBM) approach is also delivered for simulating the determination of nonlinear system problems faced in developing liquid and supplementary algebraic dynamics domains. The rate of entropy formation rises as the magnetic field parameter and radiation parameter increase. Entropy production rate decreases as the Brinkman number and Hall current parameter become more enriched. The thermal efficiency of ternary HNFs compared to conventional HNFs losses to a low of 4.8% and peaks to 5.2%. © 2022, The Author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supervised machine learning based routing detection for smart meter network 12

Supervised machine learning based routing detection for smar...

引用

12th EAI International Conference on Mobile Multimedia Communications, MOBImedia 2019

作者： Hasan, Md Raqibull Zhao, Yanxiao Wang, Guodong Luo, Yu Pu, Lina Wang, Rui Department of Electrical and Computer Engineering South Dakota School of Mines and Technology United States Department of Electrical and Computer Engineering Virginia Commonwealth University United States Department of Computer Science Massachusetts College of Liberal Arts United States Department of Electrical and Computer Engineering Mississippi State University United States School of Computing Sciences and Computer Engineering University of Southern Mississippi United States College of Information Engineering and Automation Civil Aviation University of China China

ISBN: (纸本)9781631901836

It is known that the Ad hoc On-Demand Distance Vector (AODV) routing protocol for smart meter network is vulnerable to denial of service attacks (e.g., black hole attack and selective forwarding attack). In this paper, we introduce supervised machine learning to detect unknown routing attacks under AODV. There are two problems in the existing intrusion detection algorithms. The first problem is that the existing intrusion detection algorithms are mainly applied to a specific and known type of routing attack, which no longer work for unknown attacks. The second one is that constant thresholds are commonly used for detection. To overcome these two problems, we introduce a supervised machine learning based detection approach. To implement supervised machine learning, three steps are involved. First, features and target estimations are selected from malicious AODV behaviors in smart meter network to generate training data sets. Second, we assign a suitable classifier including support vector machine, k-nearest neighbors and decision trees to fit the training and predicted data. Third, we update our training data to maintain a dynamic threshold. Simulations are conducted using Python3.6 to evaluate the accuracy and the time overhead of our proposed supervised machine learning model. The simulation results show that the decision trees algorithm assures 100% accuracy with minimum time overhead to detect routing attacks in AODV. © 2019 EAI.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Topological descriptors for Parkinson⇔s disease classification and regression analysis

arXiv

引用

arXiv 2020年

作者： Nawar, Afra Rahman, Farhan Krishnamurthi, Narayanan Som, Anirudh Turaga, Pavan School of Electrical Computer and Energy Engineering Arizona State University School of Computing Informatics and Decision Systems Engineering Arizona State University Edson College of Nursing and Health Innovation Arizona State University School of Arts Media and Engineering Arizona State University

At present, the vast majority of human subjects with neurological disease are still diagnosed through in-person assessments and qualitative analysis of patient data. In this paper, we propose to use Topological Data Analysis (TDA) together with machine learning tools to automate the process of Parkinson’s disease classification and severity assessment. An automated, stable, and accurate method to evaluate Parkinson’s would be significant in streamlining diagnoses of patients and providing families more time for corrective measures. We propose a methodology which incorporates TDA into analyzing Parkinson’s disease postural shifts data through the representation of persistence images. Studying the topology of a system has proven to be invariant to small changes in data and has been shown to perform well in discrimination tasks. The contributions of the paper are twofold. We propose a method to 1) classify healthy patients from those afflicted by disease and 2) diagnose the severity of disease. We explore the use of the proposed method in an application involving a Parkinson’s disease dataset comprised of healthy-elderly, healthy-young and Parkinson’s disease patients. Our code is available at https://***/itsmeafra/Sublevel-Set-TDA. Copyright © 2020, The Authors. All rights reserved.

关键词： Hospital data processing

来源：评论

学校读者我要写书评

暂无评论

A Digital Personal Assistant using Bangla Voice Command Recognition and Face Detection

A Digital Personal Assistant using Bangla Voice Command Reco...

引用

2019 IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2019

作者： Gupta, Dipankar Hossain, Emam Hossain, Mohammad Shahadat Andersson, Karl Hossain, Sazzad Port City International University Department of Computer Science and Engineering Chattogram Bangladesh University of Chittagong Department of Computer Science and Engineering Chattogram Bangladesh Luleå University of Technology Department of Computer Science Electrical and Space Engineering Skelleftea Sweden University of Liberal Arts Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9781728158518

Though speech recognition has been a common interest of researchers over the last couple of decades, but very few works have been done on Bangla voice recognition. In this research, we developed a digital personal assistant for handicapped people which recognizes continuous Bangla voice commands. We employed the cross-correlation technique which compares the energy of Bangla voice commands with prerecorded reference signals. After recognizing a Bangla command, it executes a task specified by that command. Mouse cursor can also be controlled using the facial movement of a user. We validated our model in three different environments (noisy, moderate and noiseless) so that the model can act naturally. We also compared our proposed model with a combined model of MFCC DTW, and another model which combines crosscorrelation with LPC. Results indicate that the proposed model achieves a huge accuracy and smaller response time comparing to the other two techniques. © 2019 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Mathematical Model with Energy and Clustering Energy Based Routing Protocols as Remediation to the Directional Source Aware Routing Protocol in Wireless Sensor Networks

引用

Wireless Sensor Network 2022年第2期14卷 23-39页

作者： Samir Haddad Jinane Sayah Bachar El-Hassan Chadi Kallab Mohamad Chakroun Nisrine Turkey Jinan Charafeddine Hani Hamdan Faculty of Arts and Sciences Department of Computer Science and Mathematics University of Balamand Koura Lebanon Issam Fares Faculty of Technology Department of Telecom and Networks University of Balamand Koura Lebanon Faculty of Engineering Branch 1 Department of Electricity and Electronics Lebanese University Lebanon Faculty of Computer Science and Electrical Engineering The University of Rostock Rostock Germany Faculty of Engineering Notre Dame University Lebanon Université Paris-Saclay P&ocirc le scientifique et technologique de Vélizy Laboratoire d'Ingénierie des Systèmes de Versailles (LISV EA4048) Vélizy France Université Paris-Saclay CentraleSupélec CNRS Laboratoire des Signaux et Systèmes (L2S UMR CNRS 8506) Gif-sur-Yvette France

In this paper, a routing protocol for wireless sensor network, baptized energy based protocol (EBP) is proposed. Wireless sensor network presents many challenges and constraints, and one of the major constraints is the routing problem. Due to the limited energy of sensor nodes, routing in this type of network shall perform efficiently to maximize the network lifetime. One of the proposed algorithms is the directional source aware routing protocol (DSAP) which, after simulation, showed a lot of limitations and drawbacks. The modified directional source aware routing protocol (MDSAP) was proposed by the authors of this paper to address some of the DSAP’s limitations but remains limited to a fixed topology, fixed source and stationary nodes. So EBP is proposed and operated under different scenarios and showed, after its simulation using TinyOS, many advantages in terms of load balancing, free looping, minimizing packet error rate and maximizing network lifetime.

关键词： Cluster DSAP Energy MDSAP Routing Sensor Network Topology Energy Based Protocol

来源：评论

学校读者我要写书评

暂无评论

TargetNet: Functional microRNA target prediction with deep neural networks

arXiv

引用

arXiv 2021年

作者： Min, Seonwoo Lee, Byunghan Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of LG AI Research Seoul07796 Korea Republic of Department of Electronic and IT Media Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of Interdisciplinary Program in Artificial Intelligence and Interdisciplinary Program in Bioinformatics Seoul National University Seoul08826 Korea Republic of

Motivation: MicroRNAs (miRNAs) play pivotal roles in gene expression regulation by binding to target sites of messenger RNAs (mRNAs). While identifying functional targets of miRNAs is of utmost importance, their prediction remains a great challenge. Previous computational algorithms have major limitations. They use conservative candidate target site (CTS) selection criteria mainly focusing on canonical site types, rely on laborious and time-consuming manual feature extraction, and do not fully capitalize on the information underlying miRNA-CTS interactions. Results: In this paper, we introduce TargetNet, a novel deep learning-based algorithm for functional miRNA target prediction. To address the limitations of previous approaches, TargetNet has three key components: (1) relaxed CTS selection criteria accommodating irregularities in the seed region, (2) a novel miRNA-CTS sequence encoding scheme incorporating extended seed region alignments, and (3) a deep residual network-based prediction model. The proposed model was trained with miRNA-CTS pair datasets and evaluated with miRNA-mRNA pair datasets. TargetNet advances the previous state-of-theart algorithms used in functional miRNA target classification. Furthermore, it demonstrates great potential for distinguishing high-functional miRNA targets. © 2021, CC BY-NC-ND.

关键词： RNA

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：